mlsanityData to 7 Oct 2026

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

arXiv 1709.02371 ↗First posted 7 Sep 2017cs.CVcited by 966

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the cur- rent optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow. PWC-Net is 17 times smaller in size and easier to train than the recent FlowNet2 model. Moreover, it outperforms all published optical flow methods on the MPI Sintel final pass and KITTI 2015 benchmarks, running at about 35 fps on Sintel resolution (1024x436) images. Our models are available on https://github.com/NVlabs/PWC-Net.

Key facts. Cited by 966 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 206; 2022: 225; 2023: 190; 2024: 153; 2025: 118; 2026: 73.

966 papers.

Sort:

By area:

  1. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  2. 2023CoTracker: It is Better to Track Togethercited by 516
  3. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  4. 2022Kubric: A scalable dataset generatorcited by 373
  5. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  6. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 281
  7. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  8. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 273
  9. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  10. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 258
  11. 2021Conditional Object-Centric Learning from Videocited by 247
  12. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
38 more
  1. 2021Keeping Your Eye on the Ball: Trajectory Attention in Video Transformerscited by 224
  2. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 223
  3. 2022VRT: A Video Restoration Transformercited by 219
  4. 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 215
  5. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 215
  6. 2024Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modelingcited by 209
  7. 2021Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentationcited by 200
  8. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
  9. 2023Tracking Everything Everywhere All at Oncecited by 190
  10. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  11. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 178
  12. 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 177
  13. 2024Motion Prompting: Controlling Video Generation with Motion Trajectoriescited by 176
  14. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 170
  15. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 169
  16. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  17. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 168
  18. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  19. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  20. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 153
  21. 2023Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generationcited by 153
  22. 2021TimeLens: Event-based Video Frame Interpolationcited by 150
  23. 2021E-RAFT: Dense Optical Flow from Event Camerascited by 149
  24. 2022FILM: Frame Interpolation for Large Motioncited by 149
  25. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  26. 2021Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learningcited by 125
  27. 2021XVFI: eXtreme Video Frame Interpolationcited by 123
  28. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  29. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  30. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  31. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  32. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  33. 2023FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimationcited by 114
  34. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  35. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 111
  36. 2022IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolationcited by 107
  37. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  38. 2021Stereo Correspondence and Reconstruction of Endoscopic Data Challengecited by 101

50 most cited of 966 All 966 (JSON)